© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60689
    Prev
    Next
    INDEX
    Explanations

    Map operations and web service endpoints

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of the token “Map” (or any word containing “Map,” e.g. in class or module names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rekte
    -0.80
     aplicable
    -0.78
     giro
    -0.77
     GeoNames
    -0.76
    Assumption
    -0.76
    ánt
    -0.75
    ḫ
    -0.73
     remp
    -0.73
    チラ
    -0.73
     Arrivals
    -0.72
    POSITIVE LOGITS
     Map
    1.00
    ToMap
    0.85
     map
    0.84
    暫
    0.81
    越是
    0.78
     MAP
    0.78
     OMG
    0.78
    Además
    0.76
    Luego
    0.76
    ("."
    0.76
    Activations Density 0.049%

    No Known Activations